A fully-automated neural spike sorting based on projection pursuit and gaussian mixture model

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

Existing algorithms for neural spike sorting have been unsatisfactory when the signal-to-noise ratio (SNR) Is low, especially for the fully automated systems. We present a novel method that shows satisfactory performance even under low SNR, and compare Its performance with the system based on principal component analysis (PCA) and fuzzy c-means (FCM) clustering algorithm. The system consists of a feature extractor that utilizes projection pursuit based on negentropy maximization, and an unsupervised classifier based on Gaussian mixture model. It is shown that the proposed feature extractor gives better performance, compared with the PCA, and the proposed combination of feature extraction and unsupervised classification yields much better performance than the PCA-FCM.

Original languageEnglish
Pages151-155
Number of pages5
DOIs
Publication statusPublished - 2005 Dec 1
Event2nd International IEEE EMBS Conference on Neural Engineering, 2005 - Arlington, VA, United States
Duration: 2005 Mar 162005 Mar 19

Other

Other2nd International IEEE EMBS Conference on Neural Engineering, 2005
CountryUnited States
CityArlington, VA
Period05/3/1605/3/19

Fingerprint

Sorting
Principal component analysis
Signal to noise ratio
Clustering algorithms
Feature extraction
Classifiers

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Kim, K. H. (2005). A fully-automated neural spike sorting based on projection pursuit and gaussian mixture model. 151-155. Paper presented at 2nd International IEEE EMBS Conference on Neural Engineering, 2005, Arlington, VA, United States. https://doi.org/10.1109/CNE.2005.1419576
Kim, Kyung Hwan. / A fully-automated neural spike sorting based on projection pursuit and gaussian mixture model. Paper presented at 2nd International IEEE EMBS Conference on Neural Engineering, 2005, Arlington, VA, United States.5 p.
@conference{55f8925d199f46b0af024c10d80d363f,
title = "A fully-automated neural spike sorting based on projection pursuit and gaussian mixture model",
abstract = "Existing algorithms for neural spike sorting have been unsatisfactory when the signal-to-noise ratio (SNR) Is low, especially for the fully automated systems. We present a novel method that shows satisfactory performance even under low SNR, and compare Its performance with the system based on principal component analysis (PCA) and fuzzy c-means (FCM) clustering algorithm. The system consists of a feature extractor that utilizes projection pursuit based on negentropy maximization, and an unsupervised classifier based on Gaussian mixture model. It is shown that the proposed feature extractor gives better performance, compared with the PCA, and the proposed combination of feature extraction and unsupervised classification yields much better performance than the PCA-FCM.",
author = "Kim, {Kyung Hwan}",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/CNE.2005.1419576",
language = "English",
pages = "151--155",
note = "2nd International IEEE EMBS Conference on Neural Engineering, 2005 ; Conference date: 16-03-2005 Through 19-03-2005",

}

Kim, KH 2005, 'A fully-automated neural spike sorting based on projection pursuit and gaussian mixture model' Paper presented at 2nd International IEEE EMBS Conference on Neural Engineering, 2005, Arlington, VA, United States, 05/3/16 - 05/3/19, pp. 151-155. https://doi.org/10.1109/CNE.2005.1419576

A fully-automated neural spike sorting based on projection pursuit and gaussian mixture model. / Kim, Kyung Hwan.

2005. 151-155 Paper presented at 2nd International IEEE EMBS Conference on Neural Engineering, 2005, Arlington, VA, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - A fully-automated neural spike sorting based on projection pursuit and gaussian mixture model

AU - Kim, Kyung Hwan

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Existing algorithms for neural spike sorting have been unsatisfactory when the signal-to-noise ratio (SNR) Is low, especially for the fully automated systems. We present a novel method that shows satisfactory performance even under low SNR, and compare Its performance with the system based on principal component analysis (PCA) and fuzzy c-means (FCM) clustering algorithm. The system consists of a feature extractor that utilizes projection pursuit based on negentropy maximization, and an unsupervised classifier based on Gaussian mixture model. It is shown that the proposed feature extractor gives better performance, compared with the PCA, and the proposed combination of feature extraction and unsupervised classification yields much better performance than the PCA-FCM.

AB - Existing algorithms for neural spike sorting have been unsatisfactory when the signal-to-noise ratio (SNR) Is low, especially for the fully automated systems. We present a novel method that shows satisfactory performance even under low SNR, and compare Its performance with the system based on principal component analysis (PCA) and fuzzy c-means (FCM) clustering algorithm. The system consists of a feature extractor that utilizes projection pursuit based on negentropy maximization, and an unsupervised classifier based on Gaussian mixture model. It is shown that the proposed feature extractor gives better performance, compared with the PCA, and the proposed combination of feature extraction and unsupervised classification yields much better performance than the PCA-FCM.

UR - http://www.scopus.com/inward/record.url?scp=33744474820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33744474820&partnerID=8YFLogxK

U2 - 10.1109/CNE.2005.1419576

DO - 10.1109/CNE.2005.1419576

M3 - Paper

SP - 151

EP - 155

ER -

Kim KH. A fully-automated neural spike sorting based on projection pursuit and gaussian mixture model. 2005. Paper presented at 2nd International IEEE EMBS Conference on Neural Engineering, 2005, Arlington, VA, United States. https://doi.org/10.1109/CNE.2005.1419576